The new approach for sensor diagnostics is presented. The approach, Enhanced Autoassociative Neural Networks (E-AANN), adds enhancement to Autoassociative Neural Networks (AANN) developed by Kramer in 1992. This enhancement allows AANN to identify faulty sensors. E-AANN uses a secondary optimization process to identify and reconstruct sensor faults. Two common types of sensor faults are investigated, drift error and shift or offset error. In the case of drift error, the sensor error occurs gradually while in the case of shift error, the sensor error occurs abruptly. EAANN catches these error types. A chiller model provided synthetic data to test the diagnostic approach under various noise level conditions. The results show that sensor faults can be detected and corrected in noisy situations with the E-AANN method described. In high noisy situations (10% to 20% noise level), E-AANN performance degrades. E-AANN performance in simple dynamic systems was also investigated. The results show that in simple dynamic situations, E-AANN identifies faulty sensors.

The new approach for sensor diagnostics is presented. The approach, Enhanced Autoassociative Neural Networks (E-AANN), adds enhancement to Autoassociative Neural Networks (AANN) developed by Kramer in 1992. This enhancement allows AANN to identify faulty sensors. E-AANN uses a secondary optimization process to identify and reconstruct sensor faults. Two common types of sensor faults are investigated, drift error and shift or offset error. In the case of drift error, the sensor error occurs gradually while in the case of shift error, the sensor error occurs abruptly. EAANN catches these error types. A chiller model provided synthetic data to test the diagnostic approach under various noise level conditions. The results show that sensor faults can be detected and corrected in noisy situations with the E-AANN method described. In high noisy situations (10% to 20% noise level), E-AANN performance degrades. E-AANN performance in simple dynamic systems was also investigated. The results show that in simple dynamic situations, E-AANN identifies faulty sensors.

The focus of this dissertation is aimed at advancing autonomous structural health monitoring. All the research is based on developing the impedance method for monitoring structural health. The impedance technique utilizes piezoelectric patches to interrogate structures of interested with high frequency excitations. These patches are bonded directly to the structure, so information about the health of the structure can be seen in the electrical impedance of the piezoelectric patch. However, traditional impedance techniques require the use of a bulky and expensive impedance analyzer. Research presented here describes efforts to miniaturize the hardware necessary for damage detection. A prototype impedance-based structural health monitoring system, incorporating wireless based communications, is fabricated and validated with experimental testing. The first steps towards a completely autonomous structural health monitoring sensor are also presented. Power harvesting from ambient energy allows a prototype to be operable from a rechargeable power source. Aerospace vehicles are equipped with thermal protection systems to isolate internal components from harsh reentry conditions. While the thermal protection systems are critical to the safety of the vehicle, finding damage in these structures presents a unique challenge. Impedance techniques will be used to detect the standard damage mechanism for one type of thermal protection system. The sensitivity of the impedance method at elevated temperatures is also investigated. Sensors are often affixed to structures as a means of identifying structural defects. However, these sensors are susceptible to damage themselves. Sensor diagnostics is a field of study directed at identifying faulty sensors. The influence of temperature on these techniques is largely unstudied. In this dissertation, a model is generated to identify damaged sensors at any temperature. A sensor diagnostics method is also adapted for use in developed hardware. The prototype used is completely digital, so standard sensor diagnostics techniques are inapplicable. A new method is developed to work with the digital hardware. / Ph. D.

This thesis deals with problems related to heating of hot service water. It focuses on solar water heating, describes individual types of solar panels and summarizes the existing information about solar water heating. It demonstrates actual problems of solar system solution on a specific example of a two-generation family house, where it analyses possibilities of diagnostics and control of such system. It also deals with suggestions of possible expansion of the current solar system.